PPCSA: Partial Participation-Based Compressed and Secure Aggregation in Federated Learning

Ahmed Moustafa, Muhammad Asad*, Saima Shaukat, Alexander Norta

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceedings published in a bookpeer-review

Abstract

Federated Learning (FL) enables users devices (UDs) to collaboratively train a Deep Learning (DL) model on an individual’s gathered data, without revealing their privacy sensitive information to the centralized cloud server. Those UDs usually have limited data plans with a slow network connection to a centralized cloud server, which causes limited communication bandwidth between the contributing mobile users. To mitigate this problem, we propose a novel Partial Participation-based Compressed and Secure Aggregation (PPCSA) algorithm. To implement the PPCSA, we use a Sparse Compression Operator (SCO) that reduces the communication bits between the cloud server and the users while maintaining the FL requirements. In particular, PPCSA utilizes a novel compression method and introduces a Local Differential Privacy (LDP) based framework to achieve the communication-efficiency at a new level. Our experiments on a commonly used FL dataset show that PPCSA distinctively outperforms the state-of-the-art schemes in terms of convergence accuracy and communication bits.

Original languageEnglish
Title of host publicationAdvanced Information Networking and Applications - Proceedings of the 35th International Conference on Advanced Information Networking and Applications, AINA-2021
EditorsLeonard Barolli, Isaac Woungang, Tomoya Enokido
PublisherSpringer Science and Business Media Deutschland GmbH
Pages345-357
Number of pages13
ISBN (Print)9783030750749
DOIs
Publication statusPublished - 2021
Event35th International Conference on Advanced Information Networking and Applications, AINA 2021 - Toronto [state] ON, Canada
Duration: 12 May 202114 May 2021

Publication series

NameLecture Notes in Networks and Systems
Volume226 LNNS
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

Conference35th International Conference on Advanced Information Networking and Applications, AINA 2021
Country/TerritoryCanada
CityToronto [state] ON
Period12/05/2114/05/21

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'PPCSA: Partial Participation-Based Compressed and Secure Aggregation in Federated Learning'. Together they form a unique fingerprint.

Cite this